INDEX

Explanations

future tense verbs indicating actions or events

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AccessException

-0.15

urr

-0.15

ertia

-0.14

indsight

-0.14

rtl

-0.14

mini

-0.14

ContentPane

-0.14

ursion

-0.14

åŃ¦ä¼ļ

-0.14

YPE

-0.13

POSITIVE LOGITS

 feature

0.20

 soon

0.19

 next

0.18

soon

0.18

 beginning

0.17

be

0.17

 Soon

0.16

umpy

0.16

 host

0.16

0.15

Activations Density 0.143%

future tense verbs indicating actions or events

No Comments

No Known Activations